Skip to main content
Glama
Sign In

MemoryBrain

by ai.memorybrain
OverviewDiscussionsAdmin

Quedarte una nota de otro cerebro

keep_note
Idempotent

Guarda en el cerebro del usuario una nota de un cerebro conectado, como fuente citada (de quién es y de dónde sale), nunca como si la hubiera escrito él. Úsala solo cuando el usuario pida quedársela. Si dice qué piensa de ella, pásalo literal en text: queda pegado a la nota como su voz.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "brain": "<brain>",
      "id": "<id>"
    },
    "name": "keep_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesEl id o la ruta de la nota en ese cerebro.
textNoLo que el usuario piensa de ella, literal (opcional).
brainYesEl cerebro conectado (p. ej. «carlos»).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-destructive, idempotent, open-world write; the description adds real context beyond that: the write lands in the user's own brain with source attribution, and any supplied `text` is stored verbatim as the user's voice attached to the note. It does not cover what happens if the note already exists or if the source brain is not connected, so it stops short of full behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each doing distinct work: the write and its attribution rule first, the usage restriction second, the `text` semantics last. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter write tool with no output schema, the definition covers purpose, trigger, attribution semantics, and the optional `text` field. Remaining gaps (duplicate handling, behavior when the connected brain is unavailable) are minor and partly mitigated by the idempotentHint annotation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds meaning for `text` beyond the schema: it must be the user's literal opinion and is stored attached to the note as their voice, which clarifies why verbatim quoting matters. `brain` and `id` are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (guarda una nota de un cerebro conectado en el cerebro del usuario) and adds the defining constraint that it is stored as a cited source, never as the user's own writing. That attribution rule alone distinguishes it from read_note and extend_note without naming them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger with a restrictive 'solo cuando el usuario pida quedársela', which is clear when-to-use guidance and implicitly excludes proactive use. It does not name the alternatives (read_note, extend_note) or say what to do when the user only wants to read the note.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MemoryBrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources